INDEX

Explanations

content related to exclusivity and exclusive access or events

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

stad

-0.17

phrase

-0.14

olute

-0.13

½Ķ

-0.13

case

-0.13

imal

-0.13

aggi

-0.13

 Baron

-0.13

.setter

-0.13

bart

-0.13

POSITIVE LOGITS

-purpose

0.15

tesy

0.15

irty

0.15

izard

0.15

yny

0.15

Bounding

0.14

yor

0.14

ubo

0.14

omba

0.14

KER

0.14

Activations Density 0.010%

content related to exclusivity and exclusive access or events

No Comments

No Known Activations